review-tests

Use when checking whether a branch is adequately tested — building and running the affected workspaces, then auditing changed code for missing test files, untested exports, untested error paths and untested routes — and reporting gaps with T-M/U/E/R/S IDs in the four-field format.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly executable test-review procedure with strong sequencing, validation checkpoints, and feedback loops. Its weakness is progressive disclosure: it is a single large file whose few external references are woven into prose instead of presented as a clean, one-level reference structure.

Suggestions

Split the convention details (testing-patterns, browser-tests, the T-M/U/E/R/S tier definitions) into a short references file and link to it from a single 'References' block so the main body stays a lean overview.

Tighten the editorial rationale passages in Step 0 and the shape-check notes to their operative sentences; the 'why' can often be one clause rather than a paragraph.

Surface the wiki/conventions pointers as a labeled list (e.g. '## Conventions referenced') rather than embedding them inside Step 4 bullets, so navigation is explicit.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes competence — executable bash and a terse finding format — but several extended editorial passages (e.g. 'The file is the deliverable… however good the audit inside it') explain rationale at a length that could be trimmed.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste bash for resolving the base, building, testing, locating tests, and verifying report shape, plus a concrete four-field finding template covering the common cases.	5 / 5
Workflow Clarity	Steps 0–4 are explicitly sequenced with validation checkpoints (`grep -c '^## ...$'` must print 5), feedback loops (restore the skeleton if clobbered, re-check before finishing), and explicit handling of the 'no step is a stop' failure mode.	5 / 5
Progressive Disclosure	Well-organized into clear sections, but the procedure is a ~200-line monolith with no bundle files to split into; wiki pointers (`wiki/conventions/testing-patterns.md`, `wiki/conventions/browser-tests.md`) are buried mid-prose rather than signaled as a navigable reference block.	3 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A precise, third-person description that names concrete actions, gives an explicit 'Use when' trigger, and carves out a distinct niche via its gap-ID taxonomy. Only slightly shy of perfect trigger-term breadth because it favors in-house jargon over everyday synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'building and running the affected workspaces', 'auditing changed code for missing test files, untested exports, untested error paths and untested routes', and 'reporting gaps with T-M/U/E/R/S IDs in the four-field format' — covering the task comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (build, run tests, audit changed code, report gaps) and 'when' ('Use when checking whether a branch is adequately tested') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Opens with a natural trigger ('Use when checking whether a branch is adequately tested') and includes 'tested', 'error paths', 'routes', but leans on specialized jargon (T-M/U/E/R/S IDs) and misses a few common synonyms a user might say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — branch test-coverage review with a specific T-M/U/E/R/S gap taxonomy and four-field report format — making it unlikely to trigger for the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xchromo/osn
Path: .claude/skills/review-tests/SKILL.md
Commit: 5438649

Reviewed: ~11 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.